Back End Engineer (Python + GCP + Gen AI)

First Soft Solutions LLC; New York (NY); On-site; USD 120,000 - 160,000; Full time

Benefits offered by this job

High-impact AI projects

Collaborative environment

Opportunity for right-to-hire

Job summary

First Soft Solutions LLC is seeking a Senior AI Engineer to create LLM-powered automation solutions that enhance operational workflows in Finance and Business Operations. This hands-on role involves developing reliable, scalable AI systems, collaborating with various teams to integrate AI-driven solutions.

The ideal candidate has 7+ years in software engineering, including significant expertise in Python and Java, and experience with LLM APIs. The position is onsite in New York, offering a right-to-hire path.

Qualifications

• 7+ years of software engineering experience with AI/LLM applications.
• Hands-on expertise in Python and Java.
• Experience with LLM APIs such as OpenAI and Claude.

Responsibilities

• Design LLM-powered agents for automating workflows.
• Develop production-grade AI applications with monitoring.
• Collaborate with teams to identify automation opportunities.

Skills

Python

Java

LLM APIs

Software Engineering

Prompt Engineering

Tools

PostgreSQL

SQL Server

GitHub Actions

Job description

AI Engineer (Senior Level)

Location: New York, NY (Onsite)

Engagement Type: Consultant Role (Right-to-Hire)

About The Role

We are seeking an experienced AI Engineer to design and build LLM-powered automation solutions that improve operational workflows across Finance and Business Operations. This is a hands‑on engineering role, focused on building reliable, scalable, and production‑ready AI systems not research.

You will work at the intersection of Software Engineering and Applied AI, developing intelligent agents that integrate with enterprise systems, automate workflows, and deliver secure, auditable, and trustworthy outputs.

This role requires close collaboration with business and engineering teams to create impactful AI‑driven solutions that support day‑to‑day operations.

Key Responsibilities

• Design and develop LLM-powered agents to automate business and operational workflows, including document processing, data validation, and exception handling.
• Build integrations between AI agents and internal systems using APIs, databases, enterprise tools, and MCP servers.
• Implement guardrails, validation frameworks, and human‑in‑the‑loop workflows to ensure reliable and trustworthy outputs.
• Develop production‑grade AI applications with strong observability, logging, monitoring, auditability, and cost tracking.
• Partner with stakeholders to identify automation opportunities & convert requirements into scalable AI solutions.
• Build reusable AI engineering frameworks, including:
  • Prompt management
  • Context orchestration
  • Output validation
  • Evaluation and testing frameworks
• Stay updated on emerging LLM technologies, tools, and APIs to recommend practical architecture and model choices.
• Collaborate with architecture and engineering teams to ensure secure integration with enterprise platforms, authentication, and governance standards.

Required Qualifications

• 7+ years of software engineering experience, including 2+ years building AI/LLM-based production applications.
• Strong hands‑on expertise in Python and Java for enterprise application development.
• Experience working with LLM APIs such as OpenAI, Claude, or similar platforms.
• Strong understanding of:
  • Prompt Engineering
  • Function/Tool Calling
  • Structured Outputs
  • Context Management
• Experience building AI Agents / LLM workflows, including:
  • Tool integrations
  • API orchestration
  • Multi‑step workflows
  • MCP server integration
• Strong knowledge of AI reliability and safety patterns, including:
  • Output validation
  • Hallucination mitigation
  • Cost optimization
  • Rate limiting
  • Audit logging
• Experience integrating enterprise systems using REST APIs, SQL databases, and messaging systems.
• Strong software engineering fundamentals:
  • Clean coding practices
  • Testing and debugging
  • CI/CD
  • Observability and monitoring
• Excellent communication skills with the ability to explain AI capabilities to technical and non‑technical stakeholders.

Preferred Qualifications

• Experience with RAG (Retrieval‑Augmented Generation) pipelines.
• Knowledge of Vector Databases and document processing systems.
• Familiarity with LLM evaluation frameworks, regression testing, and human review systems.
• Experience in Financial Services, Operations, or highly regulated environments.
• Exposure to workflow orchestration tools such as Temporal.

Technology Environment

Languages: Python, Java

LLM Platforms: Claude, OpenAI, Enterprise AI Models

Integrations: MCP Servers, REST APIs

Databases: PostgreSQL, SQL Server

Cloud/Infrastructure: AKS, Enterprise Data Platforms

DevOps: GitHub Actions, CI/CD Pipelines

Monitoring: Logging & Observability Tools

Why Join Us?

• Work on high‑impact AI automation initiatives within Finance and Operations.
• Build production‑grade AI systems used by enterprise teams daily.
• Collaborate with experienced engineering and business leaders.
• Opportunity to contribute in a high‑ownership role with a right‑to‑hire path.